Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112654
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рах
    -0.08
    Placed
    -0.07
    _PLL
    -0.07
     reform
    -0.07
    _FL
    -0.07
    =(
    -0.07
    _{
    -0.07
     Salam
    -0.07
    ensions
    -0.07
    placements
    -0.07
    POSITIVE LOGITS
     senden
    0.08
     analys
    0.08
     dituz
    0.08
     leeyahay
    0.08
    rechts
    0.08
    ibilidad
    0.08
     Municipalidad
    0.08
     থেক
    0.08
    hebb
    0.08
     tiy
    0.08
    Activations Density 0.020%

    No Known Activations